Apparatus, method, and computer readable medium

Abstract

Provided is an apparatus including: an acquisition unit which acquires measurement data indicating a state of a target; a supply unit which supplies the measurement data acquired by the acquisition unit to a plurality of classification models respectively learned by learning data, which includes measurement data in a period in which the state of the target is normal, for periods different from each other, the plurality of classification models classifying measurement data as either normal or abnormal in response to the measurement data being input; and a determination unit which determines the state of the target as either normal or abnormal based on a plurality of classification results output from the plurality of classification models.

What is claimed is: 
     
         1 . An apparatus comprising:
 an acquisition unit which acquires measurement data indicating a state of a target;   a supply unit which supplies the measurement data acquired by the acquisition unit to a plurality of classification models respectively learned by learning data, which includes measurement data in a period in which the state of the target is normal, for periods different from each other, the plurality of classification models classifying measurement data as either normal or abnormal in response to the measurement data being input; and   a determination unit which determines the state of the target as either normal or abnormal based on a plurality of classification results output from the plurality of classification models.   
     
     
         2 . The apparatus according to  claim 1 , further comprising a learning processing unit which generates, in each period in which the state of the target is normal, a new classification model to be included in the plurality of classification models by learning processing using learning data including measurement data in the period acquired by the acquisition unit. 
     
     
         3 . The apparatus according to  claim 1 , further comprising a selection unit which selects the plurality of classification models from two or more classification models respectively learned by learning data, which includes measurement data in a period in which the state of the target is normal, for periods different from each other, the two or more classification models classifying measurement data as either normal or abnormal in response to the measurement data being input. 
     
     
         4 . The apparatus according to  claim 3 , wherein the selection unit selects, as at least one of the plurality of classification models, at least one classification model learned by learning data including measurement data in a most recent period. 
     
     
         5 . The apparatus according to  claim 3 , wherein the selection unit selects, as at least one of the plurality of classification models, at least one classification model designated by an operator among the two or more classification models. 
     
     
         6 . The apparatus according to  claim 1 , wherein the determination unit determines the state of the target as either normal or abnormal by taking a logical product of the plurality of classification results. 
     
     
         7 . The apparatus according to  claim 1 , wherein the determination unit determines the state of the target as either normal or abnormal by making a majority decision of the plurality of classification results. 
     
     
         8 . The apparatus according to  claim 7 , wherein the determination unit determines the state of the target as either normal or abnormal by adding a larger weight to a classification result of a classification model learned by learning data including measurement data in a more recent period among the plurality of classification models, and making a weighted majority decision of the plurality of classification results. 
     
     
         9 . The apparatus according to  claim 1 , further comprising a decision unit which decides a severity of an abnormal state of the target, based on a number of at least one time of consecutive determination that the state of the target is abnormal. 
     
     
         10 . The apparatus according to  claim 9 , further comprising a setting unit which sets, as measurement data to be included in new learning data, any one of measurement data in a period in which the severity decided by the decision unit is lower than a reference severity among the measurement data in each period acquired by the acquisition unit and supplied from the supply unit to the plurality of classification models, or measurement data obtained by excluding each piece of measurement data, which has caused consecutive abnormality determination until the severity decided by the decision unit reaches the reference severity, and each piece of measurement data, which is subsequent to the each piece of measurement data, which has caused consecutive abnormality determination until the severity reaches the reference severity, and has caused consecutive abnormality determination, among the measurement data acquired by the acquisition unit and supplied from the supply unit to the plurality of classification models. 
     
     
         11 . A method comprising:
 acquiring measurement data indicating a state of a target;   supplying the measurement data acquired in the acquiring to a plurality of classification models respectively learned by learning data, which includes measurement data in a period in which the state of the target is normal, for periods different from each other, the plurality of classification models classifying measurement data as either normal or abnormal in response to the measurement data being input; and   determining the state of the target as either normal or abnormal based on a plurality of classification results output from the plurality of classification models.   
     
     
         12 . A computer readable medium having recorded thereon a program that, when executed by a computer, causes the computer to function as:
 an acquisition unit which acquires measurement data indicating a state of a target;   a supply unit which supplies the measurement data acquired by the acquisition unit to a plurality of classification models respectively learned by learning data, which includes measurement data in a period in which the state of the target is normal, for periods different from each other, the plurality of classification models classifying measurement data as either normal or abnormal in response to the measurement data being input; and   a determination unit which determines the state of the target as either normal or abnormal based on a plurality of classification results output from the plurality of classification models.